iwlwifi: mvm: defer setting IWL_MVM_STATUS_IN_HW_RESTART

A hardware/firmware error may happen at any point in time. In
particular, it might happen while mac80211 is in the middle of
a flow. We observed the following situation:
 * mac80211 is in authentication flow, in ieee80211_prep_connection()
 * iwlwifi firmware crashes, but no error can be reported at this
   precise point (mostly because the driver method is void, but even
   if it wasn't we'd just shift to a race condition)
 * mac80211 continues the flow, trying to add the AP station
 * iwlwifi has already set its internal restart flag, and so thinks
   that adding the station is part of the restart and already set up,
   so it uses the information that's supposed to already be in the
   struct

This can happen with any flow in mac80211 and with any information
we try to preserve across hardware restarts.

To fix this, only set a new HW_RESTART_REQUESTED flag and translate
that to IN_HW_RESTART once mac80211 actually starts the restart by
calling our start() method. As a consequence, any mac80211 flow in
progress at the time of the restart will properly finish (certainly
with errors), before the restart is attempted.

This fixes https://bugzilla.kernel.org/show_bug.cgi?id=195299.
Reported-by: Ndjagoo <dev@djagoo.io>
Reported-by: NŁukasz Siudut <lsiudut@gmail.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NLuca Coelho <luciano.coelho@intel.com>

drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c

@@ -1084,7 +1084,13 @@ int __iwl_mvm_mac_start(struct iwl_mvm *mvm)
 
 	lockdep_assert_held(&mvm->mutex);
 
-	if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
+	if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status)) {
+		/*
+		 * Now convert the HW_RESTART_REQUESTED flag to IN_HW_RESTART
+		 * so later code will - from now on - see that we're doing it.
+		 */
+		set_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status);
+		clear_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
 		/* Clean up some internal and mac80211 state on restart */
 		iwl_mvm_restart_cleanup(mvm);
 	} else {

drivers/net/wireless/intel/iwlwifi/mvm/mvm.h

@@ -1090,6 +1090,7 @@ struct iwl_mvm {
  * @IWL_MVM_STATUS_HW_RFKILL: HW RF-kill is asserted
  * @IWL_MVM_STATUS_HW_CTKILL: CT-kill is active
  * @IWL_MVM_STATUS_ROC_RUNNING: remain-on-channel is running
+ * @IWL_MVM_STATUS_HW_RESTART_REQUESTED: HW restart was requested
  * @IWL_MVM_STATUS_IN_HW_RESTART: HW restart is active
  * @IWL_MVM_STATUS_IN_D0I3: NIC is in D0i3
  * @IWL_MVM_STATUS_ROC_AUX_RUNNING: AUX remain-on-channel is running
@@ -1101,6 +1102,7 @@ enum iwl_mvm_status {
 	IWL_MVM_STATUS_HW_RFKILL,
 	IWL_MVM_STATUS_HW_CTKILL,
 	IWL_MVM_STATUS_ROC_RUNNING,
+	IWL_MVM_STATUS_HW_RESTART_REQUESTED,
 	IWL_MVM_STATUS_IN_HW_RESTART,
 	IWL_MVM_STATUS_IN_D0I3,
 	IWL_MVM_STATUS_ROC_AUX_RUNNING,

drivers/net/wireless/intel/iwlwifi/mvm/ops.c

@@ -1235,9 +1235,8 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 	 */
 	if (!mvm->fw_restart && fw_error) {
 		iwl_mvm_fw_dbg_collect_desc(mvm, &iwl_mvm_dump_desc_assert,
-					    NULL);
-	} else if (test_and_set_bit(IWL_MVM_STATUS_IN_HW_RESTART,
-				    &mvm->status)) {
+					NULL);
+	} else if (test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)) {
 		struct iwl_mvm_reprobe *reprobe;
 
 		IWL_ERR(mvm,
@@ -1268,6 +1267,7 @@ void iwl_mvm_nic_restart(struct iwl_mvm *mvm, bool fw_error)
 
 		if (fw_error && mvm->fw_restart > 0)
 			mvm->fw_restart--;
+		set_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED, &mvm->status);
 		ieee80211_restart_hw(mvm->hw);
 	}
 }